Transcribe recorded audio files to text via Doubao Seed-ASR 2.0 (豆包录音文件识别模型2.0) from ByteDance/Volcengine. Best-in-class Chinese speech recognition with spea...
- Expanded and clarified the skill description to better detail use cases, keywords, and when to use the skill (including speaker diarization and various audio file types). - Updated Chinese and English instructions for accuracy, emphasizing usage even when "transcribe" is not explicitly mentioned. - No behavioral or code changes—documentation and usage trigger improvements only.